calc.lib.score.scorepipeline

Attributes

logger

Classes

ScorePipeline

Functions

get_variants_from_zarr(...)

Module Contents

class calc.lib.score.scorepipeline.ScorePipeline(max_memory_gb: float, threads: int, out_dir: pgscatalog.calc.lib.types.Pathish, minimum_samples_for_impute: int = 50)

calculate_scores() → None

export_full_match_log(out_directory: pgscatalog.calc.lib.types.Pathish) → None

export_scores(out_path: pgscatalog.calc.lib.types.Pathish) → None

export_summary_match_log(out_path: pgscatalog.calc.lib.types.Pathish) → None

load_scores(scorefile_paths: pgscatalog.calc.lib.types.Pathish | pgscatalog.calc.lib.types.PathishList) → None

Copy scores processed with pgscatalog-format into a duckDB database table ‘scorevariants’

match_variants(match_ambiguous: bool = False, match_multiallelic: bool = False, min_overlap: float = 0.75) → None

property db_path: pathlib.Path

property genotypes_root: zarr.Group

property genotypes_root_path: str

property out_dir: pathlib.Path

property sampleset: str

Read sampleset name from the zarr directory

property samplesets: list[str]

Get samplesets in the zarr store

property target_variants_columns: list[str]

calc.lib.score.scorepipeline.get_variants_from_zarr(group: zarr.Group) → collections.abc.Generator[tuple[str, dict[str, numpy.typing.NDArrayLike]], None, None]

calc.lib.score.scorepipeline.logger